Improving Long-Tailed Classification from Instance Level

by   Yan Zhao, et al.

Data in the real world tends to exhibit a long-tailed label distribution, which poses great challenges for neural networks in classification. Existing methods tackle this problem mainly from the coarse-grained class level, ignoring the difference among instances, e.g., hard samples vs. easy samples. In this paper, we revisit the long-tailed problem from the instance level and propose two instance-level components to improve long-tailed classification. The first one is an Adaptive Logit Adjustment (ALA) loss, which applies an adaptive adjusting term to the logit. Different from the adjusting terms in existing methods that are class-dependent and only focus on tail classes, we carefully design an instance-specific term and add it on the class-dependent term to make the network pay more attention to not only tailed class, but more importantly hard samples. The second one is a Mixture-of-Experts (MoE) network, which contains a multi-expert module and an instance-aware routing module. The routing module is designed to dynamically integrate the results of multiple experts according to each input instance, and is trained jointly with the experts network in an end-to-end manner.Extensive experiment results show that our method outperforms the state-of-the-art methods by 1 long-tailed benchmarks including ImageNet-LT and iNaturalist.



There are no comments yet.


page 1

page 2

page 3

page 4


Long-tailed Recognition by Routing Diverse Distribution-Aware Experts

Natural data are often long-tail distributed over semantic classes. Exis...

Trustworthy Long-Tailed Classification

Classification on long-tailed distributed data is a challenging problem,...

Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification

In real-world scenarios, data tends to exhibit a long-tailed, imbalanced...

ELF: An Early-Exiting Framework for Long-Tailed Classification

The natural world often follows a long-tailed data distribution where on...

Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

Long-tailed instance segmentation is a challenging task due to the extre...

Robust Long-Tailed Learning under Label Noise

Long-tailed learning has attracted much attention recently, with the goa...

L2P: An Algorithm for Estimating Heavy-tailed Outcomes

Many real-world prediction tasks have outcome (a.k.a. target or response...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.